Related Experiment Video
Updated: Jul 9, 2026
12:45
Detection and Quantification of Tunneling Nanotubes Using 3D Volume View Images
Published on: August 31, 2022
Automatic centerline extraction of irregular tubular structures using probability volumes from multiphoton imaging
A Santamaría-Pang1, C M Colbert, P Saggau
1Computational Biomedicine Lab, Dept. of CS, Univ. of Houston, Houston, TX, USA.
Medical Image Computing and Computer-Assisted Intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
|November 30, 2007
Summary
This study introduces a novel framework for extracting 3D centerlines from volumetric data without prior segmentation or shape assumptions. The method significantly improves centerline extraction for irregular tubular structures in various imaging modalities.
Area of Science:
- Medical Imaging
- Computer Vision
- Computational Anatomy
Background:
- Accurate centerline extraction is crucial for analyzing tubular structures in 3D datasets.
- Existing methods often rely on prior segmentation or assume specific tubular shapes, limiting their applicability.
Purpose of the Study:
- To develop a general framework for robust 3D centerline extraction from volumetric data.
- To overcome limitations of existing methods by not requiring prior segmentation or specific shape assumptions.
Main Methods:
- A morphology-guided level set model is employed for centerline extraction.
- The approach involves learning structural patterns and estimating centerlines as minimal cost paths using the Eikonal equation.
Main Results:
- The proposed method demonstrates substantial improvements over existing approaches.
- Significant enhancements were observed, particularly for irregular tubular objects in synthetic, CT, and multiphoton 3D images.
Conclusions:
- The developed framework offers a versatile and effective solution for 3D centerline extraction.
- This method advances the analysis of complex tubular structures in diverse volumetric imaging applications.
